{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XVRJXO5HC7DC7BJXPVGM4YV4IP","short_pith_number":"pith:XVRJXO5H","schema_version":"1.0","canonical_sha256":"bd629bbba717c62f85377d4cce62bc43ef53fb6a57b43a9e9ea1cd0d4a0be844","source":{"kind":"arxiv","id":"2506.07154","version":1},"attestation_state":"computed","paper":{"title":"Syntactic Control of Language Models by Posterior Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Afra Amini, Ryan Cotterell, Tim Vieira, Vicky Xefteri","submitted_at":"2025-06-08T14:01:34Z","abstract_excerpt":"Controlling the syntactic structure of text generated by language models is valuable for applications requiring clarity, stylistic consistency, or interpretability, yet it remains a challenging task. In this paper, we argue that sampling algorithms based on the posterior inference can effectively enforce a target constituency structure during generation. Our approach combines sequential Monte Carlo, which estimates the posterior distribution by sampling from a proposal distribution, with a syntactic tagger that ensures that each generated token aligns with the desired syntactic structure. Our "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.07154","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-08T14:01:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d16c1cd5b755983fd75c7ba3fc22fc8a1c531d70b6bc7d66fa51fd62cef9a22f","abstract_canon_sha256":"0bde4e6bb6fd9d92112457aed3286573018e067b58bbd3c7983d1ea9a4dae0f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:02.620464Z","signature_b64":"pGBwDxpDMoifgbkQ+FKREzUQSv/8T9vqFQRntCrMuBvznXcMVoAijJYobB7Km0USTo1mfFOgw9oCCqvc6Z7EBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd629bbba717c62f85377d4cce62bc43ef53fb6a57b43a9e9ea1cd0d4a0be844","last_reissued_at":"2026-07-05T11:18:02.619965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:02.619965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Syntactic Control of Language Models by Posterior Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Afra Amini, Ryan Cotterell, Tim Vieira, Vicky Xefteri","submitted_at":"2025-06-08T14:01:34Z","abstract_excerpt":"Controlling the syntactic structure of text generated by language models is valuable for applications requiring clarity, stylistic consistency, or interpretability, yet it remains a challenging task. In this paper, we argue that sampling algorithms based on the posterior inference can effectively enforce a target constituency structure during generation. Our approach combines sequential Monte Carlo, which estimates the posterior distribution by sampling from a proposal distribution, with a syntactic tagger that ensures that each generated token aligns with the desired syntactic structure. Our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07154","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.07154/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.07154","created_at":"2026-07-05T11:18:02.620023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07154v1","created_at":"2026-07-05T11:18:02.620023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07154","created_at":"2026-07-05T11:18:02.620023+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVRJXO5HC7DC","created_at":"2026-07-05T11:18:02.620023+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVRJXO5HC7DC7BJX","created_at":"2026-07-05T11:18:02.620023+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVRJXO5H","created_at":"2026-07-05T11:18:02.620023+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVRJXO5HC7DC7BJXPVGM4YV4IP","json":"https://pith.science/pith/XVRJXO5HC7DC7BJXPVGM4YV4IP.json","graph_json":"https://pith.science/api/pith-number/XVRJXO5HC7DC7BJXPVGM4YV4IP/graph.json","events_json":"https://pith.science/api/pith-number/XVRJXO5HC7DC7BJXPVGM4YV4IP/events.json","paper":"https://pith.science/paper/XVRJXO5H"},"agent_actions":{"view_html":"https://pith.science/pith/XVRJXO5HC7DC7BJXPVGM4YV4IP","download_json":"https://pith.science/pith/XVRJXO5HC7DC7BJXPVGM4YV4IP.json","view_paper":"https://pith.science/paper/XVRJXO5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07154&json=true","fetch_graph":"https://pith.science/api/pith-number/XVRJXO5HC7DC7BJXPVGM4YV4IP/graph.json","fetch_events":"https://pith.science/api/pith-number/XVRJXO5HC7DC7BJXPVGM4YV4IP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVRJXO5HC7DC7BJXPVGM4YV4IP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVRJXO5HC7DC7BJXPVGM4YV4IP/action/storage_attestation","attest_author":"https://pith.science/pith/XVRJXO5HC7DC7BJXPVGM4YV4IP/action/author_attestation","sign_citation":"https://pith.science/pith/XVRJXO5HC7DC7BJXPVGM4YV4IP/action/citation_signature","submit_replication":"https://pith.science/pith/XVRJXO5HC7DC7BJXPVGM4YV4IP/action/replication_record"}},"created_at":"2026-07-05T11:18:02.620023+00:00","updated_at":"2026-07-05T11:18:02.620023+00:00"}